Bridge between early 1B studies and self studies
6 agents, 12 issues
Method changes:
First instructions now include reference to political party (either Democratic or Republican”: “On the screens that follow you’re going to learn about a collection of registered [party] we polled on a series of political issues.”
After completing the new agent task, participants then selected the party they most identified with (Democratic, Republican, Independent, or none of these) and reported how strongly they identify with their party on a sliding scale from “not at all” to “very strongly”.
PNS scale added.
| 0 (N=57) |
0.25 (N=46) |
0.5 (N=54) |
0.75 (N=59) |
1 (N=61) |
Overall (N=277) |
|
|---|---|---|---|---|---|---|
| age | ||||||
| Mean (SD) | 35.4 (12.8) | 40.0 (16.7) | 37.1 (12.1) | 38.5 (11.3) | 36.8 (12.1) | 37.5 (12.9) |
| Median [Min, Max] | 32.0 [20.0, 76.0] | 37.0 [18.0, 84.0] | 33.5 [20.0, 74.0] | 37.0 [22.0, 71.0] | 33.0 [20.0, 74.0] | 35.0 [18.0, 84.0] |
| race | ||||||
| Asian | 1 (1.8%) | 6 (13.0%) | 4 (7.4%) | 2 (3.4%) | 4 (6.6%) | 17 (6.1%) |
| Black or African-American | 9 (15.8%) | 4 (8.7%) | 4 (7.4%) | 6 (10.2%) | 7 (11.5%) | 30 (10.8%) |
| Hispanic/Latinx | 3 (5.3%) | 1 (2.2%) | 5 (9.3%) | 3 (5.1%) | 2 (3.3%) | 14 (5.1%) |
| Other | 1 (1.8%) | 0 (0%) | 0 (0%) | 2 (3.4%) | 0 (0%) | 3 (1.1%) |
| White | 43 (75.4%) | 33 (71.7%) | 40 (74.1%) | 44 (74.6%) | 48 (78.7%) | 208 (75.1%) |
| American Indian or Alaska Native | 0 (0%) | 1 (2.2%) | 1 (1.9%) | 2 (3.4%) | 0 (0%) | 4 (1.4%) |
| Native Hawaiian or Other Pacific Islander | 0 (0%) | 1 (2.2%) | 0 (0%) | 0 (0%) | 0 (0%) | 1 (0.4%) |
| gender | ||||||
| Another gender not listed here | 1 (1.8%) | 0 (0%) | 0 (0%) | 0 (0%) | 0 (0%) | 1 (0.4%) |
| Man | 24 (42.1%) | 25 (54.3%) | 33 (61.1%) | 24 (40.7%) | 29 (47.5%) | 135 (48.7%) |
| Non-binary | 1 (1.8%) | 0 (0%) | 0 (0%) | 2 (3.4%) | 1 (1.6%) | 4 (1.4%) |
| Woman | 31 (54.4%) | 20 (43.5%) | 20 (37.0%) | 33 (55.9%) | 31 (50.8%) | 135 (48.7%) |
| Prefer not to answer | 0 (0%) | 1 (2.2%) | 1 (1.9%) | 0 (0%) | 0 (0%) | 2 (0.7%) |
| 0 (N=3) |
0.25 (N=3) |
0.5 (N=7) |
0.75 (N=6) |
1 (N=2) |
Overall (N=21) |
|
|---|---|---|---|---|---|---|
| age | ||||||
| Mean (SD) | 36.0 (8.54) | 54.7 (27.6) | 35.0 (12.9) | 34.0 (19.4) | 29.0 (0) | 37.1 (16.9) |
| Median [Min, Max] | 35.0 [28.0, 45.0] | 67.0 [23.0, 74.0] | 33.0 [20.0, 55.0] | 25.5 [18.0, 67.0] | 29.0 [29.0, 29.0] | 32.0 [18.0, 74.0] |
| race | ||||||
| White | 3 (100%) | 2 (66.7%) | 6 (85.7%) | 4 (66.7%) | 1 (50.0%) | 16 (76.2%) |
| Black or African-American | 0 (0%) | 1 (33.3%) | 0 (0%) | 0 (0%) | 1 (50.0%) | 2 (9.5%) |
| Native Hawaiian or Other Pacific Islander | 0 (0%) | 0 (0%) | 1 (14.3%) | 0 (0%) | 0 (0%) | 1 (4.8%) |
| Hispanic/Latinx | 0 (0%) | 0 (0%) | 0 (0%) | 2 (33.3%) | 0 (0%) | 2 (9.5%) |
| gender | ||||||
| Man | 2 (66.7%) | 2 (66.7%) | 4 (57.1%) | 2 (33.3%) | 1 (50.0%) | 11 (52.4%) |
| Woman | 1 (33.3%) | 1 (33.3%) | 3 (42.9%) | 3 (50.0%) | 1 (50.0%) | 9 (42.9%) |
| Non-binary | 0 (0%) | 0 (0%) | 0 (0%) | 1 (16.7%) | 0 (0%) | 1 (4.8%) |
Analysis of Deviance Table (Type II Wald chisquare tests)
Response: corrresp
Chisq Df Pr(>Chisq)
opinion_round 91.3318 1 < 2.2e-16 ***
Deviant_threshold 23.4286 4 0.000104 ***
opinion_round:Deviant_threshold 2.5451 4 0.636587
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 1 opinion_round.trend SE df asymp.LCL asymp.UCL z.ratio p.value
overall 0.0837 0.00894 Inf 0.0661 0.101 9.361 <.0001
Results are averaged over the levels of: Deviant_threshold
Confidence level used: 0.95 $emmeans
Deviant_threshold emmean SE df asymp.LCL asymp.UCL z.ratio p.value
0 1.446 0.1042 Inf 1.242 1.65 13.883 <.0001
0.25 1.187 0.1149 Inf 0.962 1.41 10.336 <.0001
0.5 1.067 0.1051 Inf 0.862 1.27 10.161 <.0001
0.75 0.925 0.1004 Inf 0.729 1.12 9.218 <.0001
1 0.868 0.0986 Inf 0.675 1.06 8.802 <.0001
Results are given on the logit (not the response) scale.
Confidence level used: 0.95
$contrasts
contrast estimate SE df asymp.LCL
Deviant_threshold0 - Deviant_threshold0.25 0.2590 0.155 Inf -0.1634
Deviant_threshold0 - Deviant_threshold0.5 0.3787 0.148 Inf -0.0244
Deviant_threshold0 - Deviant_threshold0.75 0.5208 0.144 Inf 0.1267
Deviant_threshold0 - Deviant_threshold1 0.5782 0.143 Inf 0.1875
Deviant_threshold0.25 - Deviant_threshold0.5 0.1197 0.155 Inf -0.3044
Deviant_threshold0.25 - Deviant_threshold0.75 0.2618 0.152 Inf -0.1538
Deviant_threshold0.25 - Deviant_threshold1 0.3192 0.151 Inf -0.0932
Deviant_threshold0.5 - Deviant_threshold0.75 0.1421 0.145 Inf -0.2539
Deviant_threshold0.5 - Deviant_threshold1 0.1995 0.144 Inf -0.1931
Deviant_threshold0.75 - Deviant_threshold1 0.0574 0.141 Inf -0.3260
asymp.UCL z.ratio p.value
0.681 1.673 0.4509
0.782 2.563 0.0774
0.915 3.605 0.0029
0.969 4.036 0.0005
0.544 0.770 0.9393
0.677 1.718 0.4226
0.732 2.111 0.2151
0.538 0.979 0.8649
0.592 1.386 0.6367
0.441 0.409 0.9942
Results are given on the log odds ratio (not the response) scale.
Confidence level used: 0.95
Conf-level adjustment: tukey method for comparing a family of 5 estimates
P value adjustment: tukey method for comparing a family of 5 estimates Type III Analysis of Variance Table with Satterthwaite's method
Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
targetpair 0 0 1 277 0.00 0.9976
Deviant_threshold 49739 49739 1 277 232.80 <2e-16 ***
targetpair:Deviant_threshold 29495 29495 1 277 138.05 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1$emtrends
targetpair Deviant_threshold.trend SE df lower.CL upper.CL t.ratio p.value
DN -57.81 3.22 277 -64.1 -51.5 -17.971 <.0001
NN -7.37 2.83 277 -12.9 -1.8 -2.606 0.0097
Degrees-of-freedom method: satterthwaite
Confidence level used: 0.95
$contrasts
contrast estimate SE df lower.CL upper.CL t.ratio p.value
DN - NN -50.4 4.29 277 -58.9 -42 -11.749 <.0001
Degrees-of-freedom method: satterthwaite
Confidence level used: 0.95 Analysis of Variance Table
Response: k
Df Sum Sq Mean Sq F value Pr(>F)
Deviant_threshold 4 21.128 5.2819 10.226 9.972e-08 ***
Residuals 272 140.486 0.5165
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1$emmeans
Deviant_threshold emmean SE df lower.CL upper.CL t.ratio p.value
0 1.63 0.0952 272 1.44 1.82 17.114 <.0001
0.25 1.85 0.1060 272 1.64 2.06 17.471 <.0001
0.5 2.14 0.0978 272 1.95 2.33 21.868 <.0001
0.75 2.16 0.0936 272 1.97 2.34 23.076 <.0001
1 2.41 0.0920 272 2.23 2.60 26.235 <.0001
Confidence level used: 0.95
$contrasts
contrast estimate SE df lower.CL
Deviant_threshold0 - Deviant_threshold0.25 -0.2222 0.142 272 -0.613
Deviant_threshold0 - Deviant_threshold0.5 -0.5096 0.136 272 -0.884
Deviant_threshold0 - Deviant_threshold0.75 -0.5301 0.133 272 -0.897
Deviant_threshold0 - Deviant_threshold1 -0.7850 0.132 272 -1.149
Deviant_threshold0.25 - Deviant_threshold0.5 -0.2874 0.144 272 -0.683
Deviant_threshold0.25 - Deviant_threshold0.75 -0.3079 0.141 272 -0.696
Deviant_threshold0.25 - Deviant_threshold1 -0.5628 0.140 272 -0.948
Deviant_threshold0.5 - Deviant_threshold0.75 -0.0205 0.135 272 -0.392
Deviant_threshold0.5 - Deviant_threshold1 -0.2754 0.134 272 -0.644
Deviant_threshold0.75 - Deviant_threshold1 -0.2549 0.131 272 -0.615
upper.CL t.ratio p.value
0.1690 -1.560 0.5246
-0.1348 -3.734 0.0021
-0.1635 -3.971 0.0009
-0.4214 -5.929 <.0001
0.1086 -1.993 0.2721
0.0803 -2.178 0.1912
-0.1774 -4.010 0.0007
0.3512 -0.151 0.9999
0.0934 -2.051 0.2448
0.1055 -1.943 0.2975
Confidence level used: 0.95
Conf-level adjustment: tukey method for comparing a family of 5 estimates
P value adjustment: tukey method for comparing a family of 5 estimates Deviant_threshold emmean SE df null t.ratio p.value
0 1.63 0.0952 272 2 -3.897 0.0001
0.25 1.85 0.1060 272 2 -1.404 0.0807
0.5 2.14 0.0978 272 2 1.418 0.9213
0.75 2.16 0.0936 272 2 1.701 0.9549
1 2.41 0.0920 272 2 4.500 1.0000
P values are left-tailed # A tibble: 2 × 8
model term estimate std.error statistic p.value conf.low conf.high
<chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 below_.5 Deviant_thre… -5.47 9.21 -0.593 0.554 -23.7 12.7
2 above_.5 Deviant_thre… -9.07 9.82 -0.924 0.357 -28.4 10.3Analysis of Variance Table
Response: confidence
Df Sum Sq Mean Sq F value Pr(>F)
deviance 4 3057 764.23 1.177 0.3212
Residuals 272 176614 649.32 $emmeans
deviance emmean SE df lower.CL upper.CL t.ratio p.value
0 53.3 3.38 272 46.6 59.9 15.786 <.0001
0.25 56.1 3.76 272 48.7 63.5 14.928 <.0001
0.5 50.5 3.47 272 43.7 57.3 14.558 <.0001
0.75 52.8 3.32 272 46.2 59.3 15.905 <.0001
1 46.1 3.26 272 39.7 52.6 14.139 <.0001
Confidence level used: 0.95
$contrasts
contrast estimate SE df lower.CL upper.CL t.ratio
deviance0 - deviance0.25 -2.806 5.05 272 -16.68 11.1 -0.556
deviance0 - deviance0.5 2.799 4.84 272 -10.49 16.1 0.578
deviance0 - deviance0.75 0.518 4.73 272 -12.48 13.5 0.109
deviance0 - deviance1 7.150 4.69 272 -5.74 20.0 1.523
deviance0.25 - deviance0.5 5.605 5.11 272 -8.43 19.6 1.096
deviance0.25 - deviance0.75 3.324 5.01 272 -10.44 17.1 0.663
deviance0.25 - deviance1 9.956 4.98 272 -3.71 23.6 2.001
deviance0.5 - deviance0.75 -2.281 4.80 272 -15.46 10.9 -0.475
deviance0.5 - deviance1 4.350 4.76 272 -8.72 17.4 0.914
deviance0.75 - deviance1 6.632 4.65 272 -6.15 19.4 1.425
p.value
0.9812
0.9781
1.0000
0.5484
0.8083
0.9640
0.2684
0.9895
0.8915
0.6119
Confidence level used: 0.95
Conf-level adjustment: tukey method for comparing a family of 5 estimates
P value adjustment: tukey method for comparing a family of 5 estimates | 0 (N=57) |
0.25 (N=46) |
0.5 (N=54) |
0.75 (N=59) |
1 (N=61) |
Overall (N=277) |
|
|---|---|---|---|---|---|---|
| pred_maj | ||||||
| Yes | 43 (75.4%) | 43 (93.5%) | 40 (74.1%) | 48 (81.4%) | 37 (60.7%) | 211 (76.2%) |
| No | 14 (24.6%) | 3 (6.5%) | 14 (25.9%) | 11 (18.6%) | 23 (37.7%) | 65 (23.5%) |
| Missing | 0 (0%) | 0 (0%) | 0 (0%) | 0 (0%) | 1 (1.6%) | 1 (0.4%) |
# A tibble: 4 × 9
# Groups: pred_maj [2]
pred_maj id term estimate std.error statistic p.value conf.low conf.high
<lgl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 FALSE below_… Devi… -13.4 16.8 -0.800 0.430 -47.8 20.9
2 FALSE above_… Devi… 3.19 15.3 0.208 0.836 -27.6 34.0
3 TRUE below_… Devi… -2.40 10.6 -0.226 0.821 -23.4 18.6
4 TRUE above_… Devi… -8.41 12.0 -0.700 0.485 -32.2 15.4Analysis of Variance Table
Response: confidence
Df Sum Sq Mean Sq F value Pr(>F)
deviance 4 3037 759.3 1.2209 0.3022550
pred_maj 1 9210 9209.9 14.8084 0.0001491 ***
deviance:pred_maj 4 1968 492.1 0.7912 0.5317347
Residuals 266 165435 621.9
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1| 0 (N=57) |
0.25 (N=46) |
0.5 (N=54) |
0.75 (N=59) |
1 (N=61) |
Overall (N=277) |
|
|---|---|---|---|---|---|---|
| pns_med | ||||||
| High | 21 (36.8%) | 22 (47.8%) | 27 (50.0%) | 33 (55.9%) | 27 (44.3%) | 130 (46.9%) |
| Low | 36 (63.2%) | 24 (52.2%) | 27 (50.0%) | 26 (44.1%) | 34 (55.7%) | 147 (53.1%) |
# A tibble: 4 × 9
# Groups: pns_med [2]
pns_med id term estimate std.error statistic p.value conf.low conf.high
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 High below_.5 Devi… 1.92 14.1 0.136 0.892 -26.2 30.1
2 High above_.5 Devi… -8.67 15.0 -0.579 0.564 -38.4 21.1
3 Low below_.5 Devi… -9.86 12.4 -0.797 0.428 -34.5 14.8
4 Low above_.5 Devi… -10.2 13.0 -0.786 0.434 -36.0 15.6Analysis of Variance Table
Response: confidence
Df Sum Sq Mean Sq F value Pr(>F)
deviance 4 3057 764.23 1.1685 0.3250
pns_med 1 918 917.83 1.4033 0.2372
deviance:pns_med 4 1069 267.17 0.4085 0.8025
Residuals 267 174628 654.04 | 0 (N=277) |
1 (N=277) |
2 (N=277) |
3 (N=277) |
4 (N=277) |
5 (N=277) |
6 (N=277) |
7 (N=277) |
8 (N=277) |
9 (N=277) |
10 (N=277) |
11 (N=277) |
Overall (N=3324) |
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| trialnum | |||||||||||||
| 0 | 58 (20.9%) | 39 (14.1%) | 33 (11.9%) | 40 (14.4%) | 37 (13.4%) | 43 (15.5%) | 57 (20.6%) | 47 (17.0%) | 48 (17.3%) | 32 (11.6%) | 46 (16.6%) | 40 (14.4%) | 520 (15.6%) |
| 1 | 50 (18.1%) | 52 (18.8%) | 54 (19.5%) | 51 (18.4%) | 38 (13.7%) | 40 (14.4%) | 49 (17.7%) | 49 (17.7%) | 51 (18.4%) | 50 (18.1%) | 41 (14.8%) | 50 (18.1%) | 575 (17.3%) |
| 2 | 41 (14.8%) | 42 (15.2%) | 49 (17.7%) | 43 (15.5%) | 45 (16.2%) | 43 (15.5%) | 33 (11.9%) | 48 (17.3%) | 37 (13.4%) | 51 (18.4%) | 34 (12.3%) | 43 (15.5%) | 509 (15.3%) |
| 3 | 44 (15.9%) | 43 (15.5%) | 53 (19.1%) | 48 (17.3%) | 49 (17.7%) | 45 (16.2%) | 61 (22.0%) | 50 (18.1%) | 46 (16.6%) | 49 (17.7%) | 51 (18.4%) | 52 (18.8%) | 591 (17.8%) |
| 4 | 39 (14.1%) | 49 (17.7%) | 48 (17.3%) | 47 (17.0%) | 46 (16.6%) | 52 (18.8%) | 40 (14.4%) | 47 (17.0%) | 50 (18.1%) | 44 (15.9%) | 40 (14.4%) | 39 (14.1%) | 541 (16.3%) |
| 5 | 45 (16.2%) | 52 (18.8%) | 40 (14.4%) | 48 (17.3%) | 62 (22.4%) | 54 (19.5%) | 37 (13.4%) | 36 (13.0%) | 45 (16.2%) | 51 (18.4%) | 65 (23.5%) | 53 (19.1%) | 588 (17.7%) |